Probablemente hay razones para no usar funciones analíticas, pero usar funciones analíticas solo :
select am, rf, rfm, rownum_rf2, rownum_rfm
from
(
-- the 3nd level takes the subproduct ranks, and for each equally ranked
-- subproduct, it produces the product ranking
select am, rf, rfm, rownum_rfm,
row_number() over (partition by rownum_rfm order by rownum_rf) rownum_rf2
from
(
-- the 2nd level ranks (without ties) the products within
-- categories, and subproducts within products simultaneosly
select am, rf, rfm,
row_number() over (partition by am order by count_rf desc) rownum_rf,
row_number() over (partition by am, rf order by count_rfm desc) rownum_rfm
from
(
-- inner most query counts the records by subproduct
-- using regular group-by. at the same time, it uses
-- the analytical sum() over to get the counts by product
select tg.am, ttc.rf, ttc.rfm,
count(*) count_rfm,
sum(count(*)) over (partition by tg.am, ttc.rf) count_rf
from tg inner join ttc on tg.value = ttc.value
group by tg.am, ttc.rf, ttc.rfm
) X
) Y
-- at level 3, we drop all but the top 5 subproducts per product
where rownum_rfm <= 5 -- top 5 subproducts
) Z
-- the filter on the final query retains only the top 10 products
where rownum_rf2 <= 10 -- top 10 products
order by am, rownum_rf2, rownum_rfm;
Utilicé rownum en lugar de rank para que nunca obtengas empates, o en otras palabras, los empates se decidirán al azar. Esto tampoco funciona si los datos no son lo suficientemente densos (menos de 5 subproductos en cualquiera de los 10 productos principales; en su lugar, puede mostrar subproductos de otros productos). Pero si los datos son densos (gran base de datos establecida), la consulta debería funcionar bien.
Lo siguiente hace dos pasadas de los datos, pero devuelve resultados correctos en cada caso. Nuevamente, esta es una consulta de clasificación sin vínculos.
select am, rf, rfm, count_rf, count_rfm, rownum_rf, rownum_rfm
from
(
-- next join the top 10 products to the data again to get
-- the subproduct counts
select tg.am, tg.rf, ttc.rfm, tg.count_rf, tg.rownum_rf, count(*) count_rfm,
ROW_NUMBER() over (partition by tg.am, tg.rf order by 1 desc) rownum_rfm
from (
-- first rank all the products
select tg.am, tg.value, ttc.rf, count(*) count_rf,
ROW_NUMBER() over (order by 1 desc) rownum_rf
from tg
inner join ttc on tg.value = ttc.value
group by tg.am, tg.value, ttc.rf
order by count_rf desc
) tg
inner join ttc on tg.value = ttc.value and tg.rf = ttc.rf
-- filter the inner query for the top 10 products only
where rownum_rf <= 10
group by tg.am, tg.rf, ttc.rfm, tg.count_rf, tg.rownum_rf
) X
-- filter where the subproduct rank is in top 5
where rownum_rfm <= 5
order by am, rownum_rf, rownum_rfm;
columnas:
count_rf : count of sales by product
count_rfm : count of sales by subproduct
rownum_rf : product rank within category (rownumber - without ties)
rownum_rfm : subproduct rank within product (without ties)
